lkml.org 
[lkml]   [2011]   [May]   [10]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [PATCHSET v3.1 0/7] data integrity: Stabilize pages during writeback for various fses
On Tue 10-05-11 10:59:15, OGAWA Hirofumi wrote:
> "Darrick J. Wong" <djwong@us.ibm.com> writes:
>
> > To assess the performance impact of stable page writes, I moved to a disk that
> > doesn't have DIF support so that I could measure just the impact of waiting for
> > writeback. I first ran wac with 64 threads madly scribbling on a 64k file and
> > saw about a 12 percent performance decrease. I then reran the wac program with
> > 64 threads and a 64MB file and saw about the same performance numbers. As I
> > suspected, the patchset only seems to impact workloads that rewrite the same
> > memory page frequently.
> >
> > I am still chasing down what exactly is broken in ext3. data=writeback mode
> > passes with no failures. data=ordered, however, does not pass; my current
> > suspicion is that jbd is calling submit_bh on data buffers but doesn't call
> > page_mkclean to kick the userspace programs off the page before writing it.
> >
> > Per various comments regarding v3 of this patchset, I've integrated his
> > suggestions, reworked the patch descriptions to make it clearer which ones
> > touch all the filesystems and which ones are to fix remaining holes in specific
> > filesystems, and expanded the scope of filesystems that got fixed.
> >
> > As always, questions and comments are welcome; and thank you to all the
> > previous reviewers of this patchset. I am also soliciting people's opinions on
> > whether or not these patches could go upstream for .40.
>
> I'd like to know those patches are on what state. Waiting in writeback
> page makes slower, like you mentioned it (I guess it would more
> noticeable if device was slower that like FAT uses). And I think
> currently it doesn't help anything others for blk-integrity stuff
> (without other technic, it doesn't help FS consistency)?
>
> So, why is this locking stuff enabled always? I think it would be better
> to enable only if blk-integrity stuff was enabled.
>
> If it was more sophisticate but more complex stuff (e.g. use
> copy-on-write technic for it), I would agree always enable though.
Well, also software RAID generally needs this feature (so that parity
information / mirror can be properly kept in sync). Not that I'd advocate
that this feature must be always enabled, it's just that there are also
other users besides blk-integrity.

Honza
--
Jan Kara <jack@suse.cz>
SUSE Labs, CR


\
 
 \ /
  Last update: 2011-05-10 14:41    [from the cache]
©2003-2011 Jasper Spaans